Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to sexual violence and harassment

    oai_token-act-pair · gpt-3.5-turbo

    references to sexual misconduct and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Dispatch
    -0.90
    ALS
    -0.77
    ICA
    -0.76
    iard
    -0.76
     Breaker
    -0.75
    GV
    -0.75
    IVERS
    -0.72
    tower
    -0.72
    REC
    -0.71
     Glob
    -0.69
    POSITIVE LOGITS
     intercourse
    1.16
     assault
    1.02
    ity
    0.99
    ized
    0.97
    ization
    0.93
     ensl
    0.91
     assaults
    0.90
     harassment
    0.90
    ities
    0.89
     misconduct
    0.89
    Act Density 0.023%

    No Known Activations